Abstract
Abstract
With of the Internet of Things (IoT) developing and the network technique progressing, malware attacks continue to occur, seriously endangering the information and property security of Internet of Things device users. To ensure the security of the Internet of Things platform and improve the efficiency of malware and vulnerability detection, a software installation threat detection model based on attention mechanism and improved convolutional neural network is constructed. Firstly, the enhanced dynamic symbolic execution module and forward program slicing algorithm are used to extract dynamic features, and then the improved convolutional neural network is utilized to classify malware. In the existing software of IoT devices, the inlining correlation function is studied using the inlining strategy, and the weight between the target pixel and the global pixel is calculated using the attention mechanism, through which the logic and correlation between the triples are correlated. Then, deep residual network is used to detect software vulnerabilities. This enables threat detection before and after software installation. In comparison with the current popular vulnerability detection model experiments, the accuracy, recall rate, accuracy rate and running time of the constructed model in the process of vulnerability detection are 0.975, 0.970, 0.968 and 0.02 s, respectively. Compared with other models, the research design model has better performance. This shows that this built model can effectively detect software installation threats, and has high detection accuracy and operation efficiency, which can provide strong support for the Internet of Things platform’s security protection.